VM-UNet: Vision Mamba UNet for Medical Image Segmentation

By Jiacheng Ruan, Jincheng Li, Suncheng Xiang. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP), 2024

971 citations recorded by the source corpus.

In the realm of medical image segmentation, both CNN-based and Transformer-based models have been extensively explored. However, CNNs exhibit limitations in long-range modeling capabilities, whereas Transformers are hampered by their quadratic computational complexity. Recently, State Space Models (SSMs), exemplified by Mamba, have emerged as a promising approach. They not only excel in modeling long-range interactions but also maintain a linear computational complexity. In this paper, leveraging state space models, we propose a U-shape architecture model for medical image segmentation, named Vision Mamba UNet (VM-UNet). Specifically, the Visual State Space (VSS) block is introduced as the foundation block to capture extensive contextual information, and an asymmetrical encoder-decoder structure is constructed with fewer convolution layers to save calculation cost. We conduct comprehensive experiments on the ISIC17, ISIC18, and Synapse datasets, and the results indicate that VM-UNet performs competitively in medical image segmentation tasks, e.g. obtaining 89.03, 89.71 and 81.08 in terms of DSC score on three datasets respectively. To our best knowledge, this is the first medical image segmentation model constructed based on the pure SSM-based model. We aim to establish a baseline and provide valuable insights for the future development of more efficient and effective SSM-based segmentation systems. Our code is available at https://github.com/JCruan519/VM-UNet.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ffaa66e698655d4b2dee1ab61448d5cc1a743a63

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Chen Qian
2. Fei Wang
3. Lefei Zhang
4. Bo Du
5. Shan You
6. Zhikang Zou
7. Tao Huang
8. Wuyang Li

Citations in the corpus

• MambaHSI: Spatial–Spectral Mamba for Hyperspectral Image Classification (2025, background): “CNN-based models are constrained by their local receptive field, which hinders their ability to model long-range dependencies [17].”
• U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation (2024, background): “At the same time, U-Mamba [56] and other works [72, 88] show superior performance in medical image segmentation.”
• LocalMamba: Visual State Space Model with Windowed Selective Scan (2024, methodology): “Leveraging Mamba’s foundation in generic models, new methodologies have been developed for visual tasks, such as image segmentation [30, 34, 40, 54] and image synthetic [14], showcasing the adaptability and effectiveness of visual Mamba models in addressing complex vision challenges.”
• PointMamba: A Simple State Space Model for Point Cloud Analysis (2024, methodology): “In this work, we focus on designing a simple State Space Model (SSM) for point cloud analysis without attention while maintaining the global modeling advantages of the Transformer.”